Moderate

Last 30 days

Uptime

100%

Response time

190 ms typical, 190 ms slowest 5%

Last check

49 min ago

Next check

any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://agent402.tools/api/moderate" \
  -H "content-type: application/json" \
  -d '{"text":"This is a perfectly normal sentence about cooking pasta."}'

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fagent402.tools%2Fapi%2Fmoderate
const res = await pay("https://agent402.tools/api/moderate", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"text":"This is a perfectly normal sentence about cooking pasta."}),
});
console.log(await res.json());

Example input

{
  "text": "This is a perfectly normal sentence about cooking pasta."
}

Example output

{
  "categories": {
    "harassment": false,
    "harassment/threatening": false,
    "hate": false,
    "hate/threatening": false,
    "self-harm": false,
    "sexual": false,
    "violence": false
  },
  "category_scores": {
    "harassment": 0.00012,
    "hate": 0.00003
  },
  "flagged": false,
  "model": "omni-moderation-latest"
}

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks